Application Of Artificial Intelligence Techniques Research Articles

Quality insights: artificial neural network and taxonomical analysis of activity networks in quality engineering

The resurgence and advancement of artificial intelligence (AI) has spurred new research interests in applying or re-applying proven techniques from the 1990s to challenges in business and industry. The area of quality engineering and technology is particularly amenable to the application of AI techniques. Quality engineering programs are predicted on recurring quality projects that are made up of specific activities. The proper management of such activities is a precursor for the success of any quality program. This research paper explores the application of the proven technique of artificial neural network to activity networking in the management of quality programs.

Forecasting ground vibration due to rock blasting: a hybrid intelligent approach using support vector regression and fuzzy C-means clustering

Ground vibration due to rock blasting is one of the main concerns in the mining operation and may cause severe damages to nearby structures and population. Therefore, accurate prediction of ground vibration plays an important role in the minimization of environmental effects of blasting in mines. Nowadays, application of artificial intelligence techniques has grown dramatically for predicting ground vibration. The researchers found that these techniques are suitable tools for accurate prediction. In this study, a hybrid model is proposed for estimating ground vibration using support vector regression (SVR) and fuzzy C-means clustering (FCM). The model is developed based on blasting data compiled from Sarcheshmeh copper mine, Iran. To demonstrate the efficiency of FCM–SVR model, this model is compared with SVR model (without data clustering) and United States Bureau of Mines empirical equation (with and without data clustering). The results show that SVR intelligent technique is more efficient and accurate than the empirical equation, and data clustering plays an effective role in accurate prediction of blast-induced ground vibration.

Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather

AbstractHigh-impact weather events, such as severe thunderstorms, tornadoes, and hurricanes, cause significant disruptions to infrastructure, property loss, and even fatalities. High-impact events can also positively impact society, such as the impact on savings through renewable energy. Prediction of these events has improved substantially with greater observational capabilities, increased computing power, and better model physics, but there is still significant room for improvement. Artificial intelligence (AI) and data science technologies, specifically machine learning and data mining, bridge the gap between numerical model prediction and real-time guidance by improving accuracy. AI techniques also extract otherwise unavailable information from forecast models by fusing model output with observations to provide additional decision support for forecasters and users. In this work, we demonstrate that applying AI techniques along with a physical understanding of the environment can significantly improve the prediction skill for multiple types of high-impact weather. The AI approach is also a contribution to the growing field of computational sustainability. The authors specifically discuss the prediction of storm duration, severe wind, severe hail, precipitation classification, forecasting for renewable energy, and aviation turbulence. They also discuss how AI techniques can process “big data,” provide insights into high-impact weather phenomena, and improve our understanding of high-impact weather.

Applications of Box–Behnken experimental design coupled with artificial neural networks for biosorption of low concentrations of cadmium using Spirulina (Arthrospira) spp.

The present study deals with the application of artificial intelligence techniques coupled with Box–Behnken (BB) design to model the processparameters for biosorption of cadmium using live Spirulina (Arthrospira) spp. as adsorbent in open race way pond with Zarrouk medium. Thebiomass concentration of Spirulina spp. decreased to half at 4 ppm Cd (II) after 8 days. Based on the LCt50 values, 3.69 ppm (8th day),Spirulina (Arthospira) maxima showed maximum tolerance. Considerable growth and bioaccumulation of Spirulina spp. is observed below1 ppm and tolerant up to 3 ppm. The cadmium adsorption on Spirulina spp. showed good correlation (R2 = 0.99) when applied to Freundlichequation and data fit into pseudo second order kinetics. A four factorial, three blocks and three level Box–Behnken design with initialconcentration (1 ppb to 5 ppb), biosorbant dosage (0.1 gdw to 0.2 gdw), agitation speed (12 rpm to 16 rpm) and pH (6 to 8) as independentvariables and percentage adsorption as dependent variable were selected for study. The data were further processed using artificial neuralnetwork model and DIRECT algorithm for better optimization. The final Cd (II) concentration of <0.5 ppb was achieved with 1 ppb initialconcentration under optimal conditions. A continuous desorption process was also developed for removal of cadmium from Spirulina (Arthrospira)sp.

NOVEL APPROACH TO IMPROVE GEOCENTRIC TRANSLATION MODEL PERFORMANCE USING ARTIFICIAL NEURAL NETWORK TECHNOLOGY

Abstract: Geocentric translation model (GTM) in recent times has not gained much popularity in coordinate transformation research due to its attainable accuracy. Accurate transformation of coordinate is a major goal and essential procedure for the solution of a number of important geodetic problems. Therefore, motivated by the successful application of Artificial Intelligence techniques in geodesy, this study developed, tested and compared a novel technique capable of improving the accuracy of GTM. First, GTM based on official parameters (OP) and new parameters determined using the arithmetic mean (AM) were applied to transform coordinate from global WGS84 datum to local Accra datum. On the basis of the results, the new parameters (AM) attained a maximum horizontal position error of 1.99 m compared to the 2.75 m attained by OP. In line with this, artificial neural network technology of backpropagation neural network (BPNN), radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) were then used to compensate for the GTM generated errors based on AM parameters to obtain a new coordinate transformation model. The new implemented models offered significant improvement in the horizontal position error from 1.99 m to 0.93 m.

Applications of Box–Behnken experimental design coupled with artificial neural networks for biosorption of low concentrations of cadmium using Spirulina (Arthrospira) spp.

The present study deals with the application of artificial intelligence techniques coupled with Box–Behnken (BB) design to model the process parameters for biosorption of cadmium using live Spirulina (Arthrospira) spp. as adsorbent in open race way pond with Zarrouk medium. The biomass concentration of Spirulina spp. decreased to half at 4 ppm Cd (II) after 8 days. Based on the LCt50 values, 3.69 ppm (8th day), Spirulina (Arthospira) maxima showed maximum tolerance. Considerable growth and bioaccumulation of Spirulina spp. is observed below 1 ppm and tolerant up to 3 ppm. The cadmium adsorption on Spirulina spp. showed good correlation (R2 = 0.99) when applied to Freundlich equation and data fit into pseudo second order kinetics. A four factorial, three blocks and three level Box–Behnken design with initial concentration (1 ppb to 5 ppb), biosorbant dosage (0.1 gdw to 0.2 gdw), agitation speed (12 rpm to 16 rpm) and pH (6 to 8) as independent variables and percentage adsorption as dependent variable were selected for study. The data were further processed using artificial neural network model and DIRECT algorithm for better optimization. The final Cd (II) concentration of <0.5 ppb was achieved with 1 ppb initial concentration under optimal conditions. A continuous desorption process was also developed for removal of cadmium from Spirulina (Arthrospira) sp.

Determining Solvency and Insolvency of Commercial Banks in Nigeria

This paper presents the application of artificial intelligence technique to develop aMulti-Layer Perceptron neural network model for determining the status (solvent or insolvent) of commercial banks in Nigeria. The common traditional classification techniques based on statistical parametric methods are constraint to fulfill certain assumptions. When those assumptions fail, the techniques do not often give sufficient descriptive accuracy in classifying the status of the banks. However, a class of feed-forward architecture of neural network known as Multi-Layer Perceptron (MLP) is not constraint by those parametric assumptions and offers good classification technique that competes well with the traditional statistical parametric techniques. In this study, data were sourced from the central bank of Nigeria and financial reports of the commercial banks in Nigeria. The banks specific variable of age, history of merger, time, total assets and total revenue are used as the input variables to the neural network. The solvency or insolvency as status are the two possible outputs of the neural network for each commercial bank in the period of 1994-2015. The developed MLP neural network model has 5 input neurons, 3 hidden neurons and 1 output neuron. Sigmoid activation function for the hidden neurons and “purelin” transfer function for the output neurons were utilized in training the MLP neural network. The results demonstrate that MLP neural networks are a viable technique for status classification of commercial banks in Nigeria.

Manufacturing operations outsourcing through an artificial team process algorithm

The successful applications of artificial intelligence techniques have been widely increased during recent years. Today, outsourcing is a common strategy to enhance competitive advantages particularly for manufacturing industries. When a manufacturer receives a number of orders from customers, an internal capacity shortage is inevitable, and then the manufacturer may decide to outsource a certain set of orders. To get the joint decision on order scheduling and operation outsourcing in a parallel machine shop, an intelligent decision making technique which is based on an artificial team process algorithm (TPA) is designed in current paper. TPA is a recently evolutionary tool where operations of exploration and an epitome-based learning behavior is employed, and the operation division between elite and plain groups is elaborated. For a successful global search, the TPA lets one group (elite) explore more global spaces, while, for fast convergence, another group (plain) is assigned to local search. So, TPA is an efficient computational-based algorithm with the potential of global search during reasonable computational efforts. Additionally, a neighborhood search algorithm (NSA) with three kinds of neighborhood structures is devised to further enhance the quality of solutions at each iteration of TPA. Furthermore, the List Scheduling (LS), as a conventional scheduler, a GA and a SA are also customized for the addressed problem as benchmark algorithms. The comparisons are carried out and the results reveal the superiority of suggested method.

Application of Artificial Intelligence Techniques for the Control of the Asynchronous Machine

The induction machine is experiencing a growing success for two decades by gradually replacing the DC machines and synchronous in many industrial applications. This paper is devoted to the study of advanced methods applied to the command of the asynchronous machine in order to obtain a system of control of high performance. While the criteria for response time, overtaking, and static error can be assured by the techniques of conventional control, the criterion of robustness remains a challenge for researchers. This criterion can be satisfied only by applying advanced techniques of command. After mathematical modeling of the asynchronous machine, it defines the control strategies based on the orientation of the rotor flux. The results of the different simulation tests highlight the properties of robustness of algorithms proposed and suggested to compare the different control strategies.

A fuzzy TOPSIS and Rough Set based approach for mechanism analysis of product infant failure

Root causes identification of product infant failure is nowadays one of the critical topics in product quality improvements. This paper puts forward a novel technical approach for mechanism analysis of product infant failure based on domain mapping in Axiomatic Design and the quality and reliability data from product lifecycle in the form of relational tree. The proposed method could intelligently decompose the early fault symptoms into root causes of critical functional parameters in function domain, design parameters in physical domain and process parameters in process domain successively. More specifically, both qualitative and quantitative attributes of quality and reliability types are considered for solving the root causes weight computation problem of product infant failure, this approach emphasizes the integrated application of artificial intelligence techniques of Rough Set and fuzzy TOPSIS to compute the weight of root causes. In order to enumerate the latent root causes of product infant failure, connotation of product infant failure based on the product reliability evolution model in the life cycle and data integration model of quality and reliability in production based on the extended QR chain are presented firstly. Then, a decomposition method for relational tree of product infant failure is studied based on domains of functional, physical and process in Axiomatic Design. The failure relation weight computation of root causes (nodes of relational tree) is considered as multi-criteria decision making problem (MCDM) by integrated application of Rough Set and fuzzy TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), which the Rough Set is used to mining the quality data and fuzzy TOPSIS is adopted to model the computation process of failure relation weight. Finally, the validity of the proposed method is verified by a case study of analyzing a car infant failure about body noise vibration harshness complaint, and the result proves that the proposed approach is conducive to improve the intelligent level of root causes identification for complex product infant failure.

Application Of Artificial Intelligence Methods In Drilling System Design And Operations: A Review Of The State Of The Art

Abstract Artificial Intelligence (AI) can be defined as the application of science and engineering with the intent of intelligent machine composition. It involves using tool based on intelligent behavior of humans in solving complex issues, designed in a way to make computers execute tasks that were earlier thought of human intelligence involvement. In comparison to other computational automations, AI facilitates and enables time reduction based on personnel needs and most importantly, the operational expenses. Artificial Intelligence (AI) is an area of great interest and significance in petroleum exploration and production. Over the years, it has made an impact in the industry, and the application has continued to grow within the oil and gas industry. The application in E &amp; P industry has more than 16 years of history with first application dated 1989, for well log interpretation; drill bit diagnosis using neural networks and intelligent reservoir simulator interface. It has been propounded in solving many problems in the oil and gas industry which includes, seismic pattern recognition, reservoir characterisation, permeability and porosity prediction, prediction of PVT properties, drill bits diagnosis, estimating pressure drop in pipes and wells, optimization of well production, well performance, portfolio management and general decision making operations and many more. This paper reviews and analyzes the successful application of artificial intelligence techniques as related to one of the major aspects of the oil and gas industry, drilling capturing the level of application and trend in the industry. A summary of various papers and reports associated with artificial intelligence applications and it limitations will be highlighted. This analysis is expected to contribute to further development of this technique and also determine the neglected areas in the field.

Applications of Artificial Intelligence Techniques to Combating Cyber Crimes: A Review

With the advances in information technology (IT) criminals are using cyberspace to commit numerous cyber crimes. Cyber infrastructures are highly vulnerable to intrusions and other threats. Physical devices and human intervention are not sufficient for monitoring and protection of these infrastructures; hence, there is a need for more sophisticated cyber defense systems that need to be flexible, adaptable and robust, and able to detect a wide variety of threats and make intelligent real-time decisions. Numerous bio-inspired computing methods of Artificial Intelligence have been increasingly playing an important role in cyber crime detection and prevention. The purpose of this study is to present advances made so far in the field of applying AI techniques for combating cyber crimes, to demonstrate how these techniques can be an effective tool for detection and prevention of cyber attacks, as well as to give the scope for future work.

The Bullwhip effect in water demand management: taming it through an artificial neural networks-based system

The Bullwhip effect (BE) refers to the amplification of the variance of orders and inventories along the supply chain as they move away from the customer. This is considered as the main cause of inefficiencies in the management of a traditional supply chain. However, the BE is not relevant in the classic system of water distribution, based on long-term supply management. Nevertheless, current circumstances have drawn a new context, which has introduced the concept of water demand management, in which efficiency and sustainability are of great importance. Then, the time horizon of management has decreased enormously and the supply time takes on an important role. Therefore, the BE must be considered, as it significantly raises the costs of management. On the one hand, this paper brings evidence that the BE appears in a system of real-time management of water demand. On the other hand, it proposes the application of artificial intelligence techniques for its reduction. More specifically, an advanced forecasting system based on artificial neural networks has been used. The BE is heavily damped.

Application of Artificial Intelligence Technique to Economic Load Dispatch of Thermal Power Generation Unit

Economic Dispatch(ED) is one of the main problem of power system operation and control which determines the optimal real power settings of generating units with an objective of minimizing the total fuel cost, subjected to limits on generator real power output & transmission losses. In all practical cases, the fuel cost of generator can be represented as a quadratic function of real power generation. This paper describe and Introduce a new nature Inspired Artificial Intelligence method called Firefly Algorithm(FA). The Firefly Algorithm is a stochastic Meta heuristic approach based on the idealized behavior of the flashing characteristics of fireflies. The aim is to minimize the generating unit’s combined fuel cost having quadratic cost characteristics subjected to limits on generator real power output & transmission losses. This paper presents an application of the FA to ED with valve point loading for different Test Case system. The obtained solution quality and computation efficiency is compared to another artificial intelligence technique, called Genetic algorithm (GA) . The simulation results show that the proposed algorithm outperforms previous artificial intelligence method.

Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEBoost technique

This paper proposes a novel method for power transformer insulation assessment using oil characteristics. A hybrid algorithm, named as SMOTEBoost is implemented in the paper to improve the diagnosis accuracy and consistency. The SMOTEBoost can significantly enhance the generalization capability of artificial intelligence (AI) algorithms for transformer insulation diagnosis. This will provide important benefits for applying AI techniques in utility companies, i.e., an AI algorithm with its model built upon on a local dataset can be utilized globally to make transformer insulation diagnosis. The SMOTEBoost adopts Synthetic Minority Over-sampling Technique (SMOTE) to handle the class imbalance problem, in which data points belonging to different fault types or insulation conditions are unevenly distributed in the training dataset. By using this boosting approach for reweighting and grouping data points in the training dataset, the SMOTEBoost facilitates AI algorithms consistently attaining desirable diagnosis accuracy. To verify the advantages of SMOTEBoost algorithm, it is integrated with a number of representative AI algorithms including support vector machine (SVM), C4.5 decision tree, radial basis function (RBF) network and k-nearest neighbor (KNN) to make transformer insulation diagnosis using various oil characteristic datasets collected from different utility companies. A statistical performance comparison amongst these algorithms is presented in the paper.

Application of artificial intelligence technique for modelling elastic properties of 2D nanoscale material

A novel computational approach is proposed to investigate the shear modulus of graphene nanostructures. In this approach, the factors that affect the shear modulus of graphene structures are analysed using an integrated artificial intelligence (AI) cluster comprising molecular dynamics (MD) and gene expression programming. The MD-based-AI approach has the ability to formulate the explicit relationship of shear modulus graphene nanostructure with respect to aspect ratio, temperature, number of atomic planes and vacancy defects. In addition, the shear modulus of graphene predicted using an integrated MD-based-AI model is in good agreement with that of experimental results obtained from the literature. The sensitivity and parametric analysis were further conducted to find out specific influence and variation of each of the input system parameters on the shear modulus of two graphene structures. It was found that the number of defects has the most dominating influence on the shear modulus of graphene nanostructure.

A Study on the Image Classification Techniques Based on Wavelet Artificial Neural Network Algorithm

With the ever-changing education information technology, it is a big problem for the universities and college that how to classify the thousands of copies of the image during the art examination marking process. This paper is to explore the application of artificial intelligence techniques, and to do accurate classification of a large number of images within a limited time and under the help of computer. It is can be seen that the proposed method is feasible through the application of the results of the actual work. Artificial neural network training Artificial neural network training methods have two mainly style, which are Incremental Training and Batch Training, and take the amount of different network training mission as the distinction standard. First, to introduce the Incremental Training [1], that means whenever the network receives the input vector and target vector, it have to adjust once the connection weights and thresholds. It is an online learning method. The other one is Batch Training [2], that means no longer adjust the connection and immediately, but perform bulk adjustment, and after a given volume of the input vector and target vector. Both training methods can be applied, whether it is static or dynamic neural network. Different results will be obtained by artificial neural network for the use of different training methods. When using artificial neural networks to solve specific problems, learning methods, training methods and artificial neural network function should be selected according to the expected results of question type and its specific requirements [3-4]. The selection of parameters of wavelet neural networks and adaptive learning

Application of Artificial Intelligence Techniques in Reactive Power/Voltage Control of Power System

&lt;p&gt;As one of the important constituents of power system automation, reactive power/voltage control possesses inherent characteristics of complexity, nonlinearity, inaccuracy and high requirement for control speed, parts of which are hard to be described by the traditional mathematical models or to be realized by routine control methods. The artificial intelligence (AI) techniques have intelligence feature which traditional method does not bear, so special attentions are paid to the application of AI techniques in reactive voltage control and a lot of results in this field are obtained. In this paper the main results and methods of applying the AI techniques, such as Expert System (ES), Artificial Neural Network (ANN), Fuzzy Theory (FT), Genetic Algorithm (GA) and Multi-Agent System (MAS), etc., to reactive voltage control in power systems are summarized, the respective application features of these techniques are analyzed and compared and some problems to be solved are pointed out.&lt;/p&gt;

Application of artificial intelligence techniques to predict the performance of RC beams shear strengthened with NSM FRP rods. Formulation of design equations

The use of near-surface mounted FRP reinforcement in reinforced concrete structures has seen a considerable increase in recent years as a strengthening method. However, few simple models have been published for predicting the shear capacity given by this technique. In this work, two different approaches are proposed. Firstly, the use of neural networks as a means of predicting shear strength without the need to use complex models is developed. Secondly, with the purpose of generating a design formula of simple application to evaluate the shear strength contribution provided by a near-surface mounted system, a multi-objective optimization problem is solved. It results from considering simultaneously the experimental results of beams with and without NSM-FRP reinforcement. The performance of both methodologies is compared with some experimental results. Sensitivity and parametric analyses are performed too for further evaluation of the proposed models.

Application of artificial intelligence to modelling asphalt–rubber viscosity

The viscosity of binder is of great importance during the handling, mixing, application and compaction of asphalt in highway surfacing. This paper presents experimental data and the application of artificial intelligence techniques (statistics, artificial neural networks (ANNs) and fuzzy logic) to modelling of apparent viscosity in asphalt–rubber binders. The binders were prepared in the laboratory by varying the rubber content (RC), rubber particle size, duration and temperature of mixture in conformity with a statistical design plan. Multi-factorial analysis of variance showed that the RC has a major influence on the viscosity observed for the considered interval of parameters variation. When only limited experimental data of design matrix are available for modelling, the fuzzy logic model is the best model to be used. In addition, the combined use of ANN and multiple regression analysis improved the characteristics of the neural network.